This work presents a reverse-time imaging technique by cross-correlating the forward wavefield with the reverse wavefield for the detection, localization, and sizing of defects in pipelines. The presented technique allows to capture the wavefield reflectivity at the places of ultrasonic wave scattering and reflections. Thus, the method is suitable for detecting pipe defects of either point-like or finite-size types using data from a pulse-echo setup. By using synthetic data generated by 3D spectral element pipe models, we show that the 3D wavefield cross-correlation imaging is capable in the case of cylindrical guided ultrasonic waves. With a ring setup of transducers, we analyze the imaging results obtained from the synthetic single-transducer and all-transducer firings. The presented pipe flaw imaging method is straightforward to carry out using a suitable wave equation solver. Also, the method does not suffer from long iterative runs and numerical convergence issues commonly connected with imaging methods based on either deterministic optimization or statistical inference. The imaging procedure can be fully baseline-free by performing data processing to remove direct arrivals from the ultrasound data.