Lung cancer is one of the deadliest cancers worldwide with high mortality rate. The survival rate can be increased if the cancer is diagnosed at early stages. Computer aided detection (CAD) system act as a secondary opinion to the radiologist for the early detection of lung nodules in Computed Tomography (CT) images. This paper provides a comprehensive review of the recent existing automated methods of identifying lung nodules from CT scans. Current detection algorithms appear to report many false positives with high sensitivity rate. Therefore, false positive reduction plays an important role in classification process. It has been analyzed that the nodule classification based on deep learning with Convolutional neural networks (CNN) is dominant due to its excellent performance.