A time-domain microwave imaging system with improved image quality is presented for early detection of breast cancer. The time-domain system has the advantage of short scan time compared with the frequency-domain system but suffers from low signal-to-noise ratio (SNR) due to high attenuation of the RF signal within the breast tissue. Signal averaging of repeated measurements can improve the SNR, but this method also smears the signal peaks due to the signal-averaged jitter, which adversely affects the reconstructed image quality. An image enhancement method using Gaussian band-pass filtering (BPF) is proposed for a time-domain imaging system. The results from the proposed method were compared with those from the deconvolution method, which is typically used to remove the effects of signal-averaged timing jitter in short pulse measurements. Simulation results with a 3D hemispherical homogeneous breast model containing tumour cells revealed improvement of the reconstructed image quality with the proposed method in the presence of timing jitter. The signal-to-mean ratio was increased from 6.46 to 14.15 with BPF, whereas deconvolution resulted in an increase to 9.36. Simulation results with a non-homogeneous realistic breast model also showed image enhancement with the proposed method.