We propose a novel method for detecting and reconstructing tubular shapes in dense, noisy, occluded and unorganized point clouds. The STEP method (Snakes for Tuboid Extraction from Point clouds) was originally designed to reconstruct woody parts of trees scanned with terrestrial LiDAR in natural forest environments. The STEP method deals with the acquisition artefacts of point clouds from terrestrial LiDAR which include three important constraints: a varying sampling rate, signal occlusion, and the presence of noise. The STEP method uses a combination of an original Hough transform and a new form of growing active contours (also referred to as ”snakes”) to overcome these constraints while being able to handle large data sets. The framework proves to be resilient under various conditions as a general shape recognition and reconstruction tool. In the field of forestry, the method was demonstrated to be robust to the previously highlighted limitations (with errors in the range of manual forest measurements, that is 1 cm diameter error). The STEP method has therefore the potential to improve current forest inventories as well as being applied to a wide array of other applications, such as pipeline reconstruction and the assessment of industrial structures.