Automated Segmentation and Classification of lung nodules into benign and malignant is a challenging task and is of vital interest for medical applications like diagnosis and surgical planning. It improves the accuracy and assist radiologist for better diagnosis. In this paper, a new method is proposed for the classification of lung nodules using Artificial Neural Networks based on Shape, Margin and Texture features. In order to reduce the complexity of the algorithm and the computational load, use of fewer features is particularly important, while maintaining an acceptable detection performance. The proposed algorithm was tested on LIDC (Lung Image Database Consortium) datasets and the results were satisfactory in terms of accuracy in classification.