Lung segmentation in Computed Tomography (CT) images is one of the important steps in Computer Aided Diagnosis (CADx) systems. This paper has proposed a completely automatic algorithm for recognition and segmentation of lungs in 3D pulmonary X-ray CT images. The advantage of this method is separation of attached nodules to the lung wall which are removed in ordinary lung segmentation methods. This method is based on thresholding algorithm that identifies attached nodules with some morphological operations. This method applied to 20 lung CT images has shown that eventually the lungs were correctly segmented. The advantage of using a simple thresholding algorithm is high speed, e.g. the time of the lung segmentation for 300 images is less than 10 seconds.