In order to improve the accuracy of the solitary pulmonary nodule diagnosis with medical signs in medical imaging diagnostics, a novel computer-aided classification method is developed. The method use features from Computed Tomography (CT) images combined with Standard Uptake Value (SUV) values in Positron Emission Tomography (PET) images to build a Support Vector Machine (SVM)classifier model. Using particle swarm optimization on SVM parametric search,thus choose the most appropriate parameters. After that will get the appropriateSVM classification model. The experimental results show that usesthetwo kinds of featuresin this study can achieve a high classification accuracy. However, the SVM classification model which after parameters optimized has higher classificationaccuracy.This method can avoid the randomness of human choice and provides a theoretical basis for the main features selected when doctors diagnosis of pulmonary nodules.