This paper focuses on characterizing the internal intensity structure of pulmonary nodules in thin-section CT images for classification between benign and malignant nodules. This approach makes use of shape index, curvedness, and CT density to represent locally each voxel constructing the three-dimensional (3D) pulmonary nodule image. From the distribution of shape index, curvedness, and CT density over the 3D pulmonary nodule image a set of histogram features, and 3D texture features is computed to classify benign and malignant nodules. Linear discriminant analysis is used for classification and a receiver operating characteristic (ROC) analysis is used to evaluate the classification accuracy. The potential usefulness of the curvature based features in the computer-aided differential diagnosis is demonstrated by using ROC curves as the performance measure.