Aim To discuss the construction of the nomogram model of coronary atherosclerotic plaque (CAP) shown on chest computed tomography (CT) and the influencing factors of plaque stability. Methods The data of patients at high risk of cardiovascular disease that received CT examination from January 2020 to October 2021 were collected for a retrospective cross-sectional study. Basic information (including gender and age), medical history, complications, blood pressure, blood biochemical indicators, etc. of the patients were collected. According to their coronary artery conditions shown by CT imaging, the patients were divided into CAP group and CAP-free group. The data were then reduced by using LASSO regression cross-validation. The nomogram model was built and validated, and its application value was evaluated by the decision curve. In the end, the influencing factors of CAP-CT value were evaluated by optimal scaling regression. Results There were 240 patients with CAP and 52 patients without CAP included in the research. After adjusting the parameter (λ＋1se), age, uric acid, estimated glomerular filtration rate (eGFR) were non-zero variables. The statistically significant age and eGFR were used to build the nomogram model. Area under ROC curve was 0.759(95%CI:0.691～0.828), sensitivity was 73.8%, specificity was 71.2%. Hosmer-Lemeshow test indicated good model fit (χ²＝11.846, P＝0.158). The prediction accuracy was 82.2%. Mean absolute error of Bootstrap resampling internal verification was 0.029. The calibration curve basically fits the ideal curve. According to the decision curve, the nomogram model shows good net benefits within the risk threshold of 0.10～0.40. Combined diabetes mellitus and β2-microglobulin (β2-MG) were independent risk factors for CAP-CT values (both P＜0.05), with the importance of 0.121 and 0.564, respectively. Conclusion Emphasis on the protection of renal function and glycemic compliance will help to reduce the formation of CAP and increase CAP stability. In particular, more attention should be paid to renal function when selecting medications.